LTX2.5-Studio / tests /test_lora_validate.py

Commit History

4 days ago

  1. fix: an adapter whose weight pairs are named lora_down/lora_up is refused at Validate, naming both namings and that this model's loader reads only lora_A/lora_B, instead of passing every check and failing inside the run with "list index out of range"

    Unverified signature
    daa617a
  2. fix: an adapter whose tensor data is cut short or out of place is refused at Validate, before any GPU time⁠

    Unverified signature
    95c2c72

5 days ago

  1. fix: the LoRA validator checks shape fit with no weights, and tells the truth before a GPU is reserved⁠

    Unverified signature
    9d84791

  1. fix: the pipeline takes PipelineQuantizationConfig, not BitsAndBytesConfig⁠

    Unverified signature
    b55f9af

  1. test: spec validator stages 5.5 and 6.5, and the revised stage 4⁠

    d86776a
  2. test: spec the mode registry, the never-empty-output invariant, app build and layering⁠

    1e0df90
  3. test: spec errors, constraints, model_files and the LoRA validator⁠

    5861856